Applied Machine Learning in EEG data Classification to Classify Major Depressive Disorder by Critical Channels

Sudhir Dhekane; Anand Khandare

doi:10.35882/jeeemi.v7i3.719

Sudhir Dhekane Thakur College of Engineering and Technology, Mumbai, India; D.J. Sanghvi College of Engineering, Mumbai, India https://orcid.org/0000-0002-9822-1826
Anand Khandare Thakur College of Engineering and Technology, Mumbai, India https://orcid.org/0000-0002-7732-8464

DOI: https://doi.org/10.35882/jeeemi.v7i3.719

Keywords: EEG channel, Multi-Layer Perceptron, Recursive Feature Elimination, Entropy

Abstract

The electroencephalogram (EEG) stands out as a promising non-invasive tool for assessing depression. However, the efficient selection of channels is crucial for pinpointing key channels that can differentiate between different stages of depression within the vast dataset. This study outcome a comprehensive strategy for optimizing EEG channels to classify Major Depressive Disorder (MDD) using machine learning (ML) and deep learning (DL) approaches, and monitor effect of central lobe channels. A thorough review underscores the vital significance of EEG channel selection in the analysis of mental disorders. Neglecting this optimization step could result in heightened computational expenses, squandered resources, and potentially inaccurate classification results. Our assessment encompassed a range of techniques, such as Asymmetric Variance Ratio (AVR), Amplitude Asymmetry Ratio (AAR), Entropy-based selection employing Probability Mass Function (PMF), and Recursive Feature Elimination (RFE) where, RFE exhibited superior performance, particularly in pinpointing the most pertinent EEG channels while including central lobe channels like Fz, Cz, and Pz. With this accuracy between 97 to 99% is recorded by Electroencephalography Neural Network (EEGNet). Our experimental findings indicate that, models using RFE achieved enhancement in accuracy to classifying depressive disorders across diverse classifiers: EEGNet (96%), Random Forest (95%), Long Short-Term Memory (LSTM: 97.4%), 1D-CNN with 95%, and Multi-Layer Perceptron (98%) irrespective of central lobe incorporation. A pivotal contribution of this research is the development of a robust Multilayer Perceptron (MLP) model trained on EEG data from 382 participants, achieved accuracy of 98.7%, with a perfect precision score of 1.00, F1-Score of 0.983, and a Recall-Score of 0.966, to make it an enhanced technique for depression classification. Significant channels identified include Fp1, Fp2, F7, F4, F8, T3, C3, Cz, T4, T5, and P3, offering critical insights about depression. Our findings shows that, optimized EEG channel selection via RFE enhances depression classification accuracy in the field of brain-computer interface.

Downloads

Download data is not yet available.

Author Biography

Anand Khandare, Thakur College of Engineering and Technology, Mumbai, India

DR. ANAND KHANDARE was received M.E. degree in Computer Engineering and Ph.D in CSE. He is currently working as Professor & Associate Dean (Planning & Operations-Digital Resources) at Thakur College of Engineering & Technology, Mumbai. His current research interest includes Machine Learning and Deep Learning, Database management, natural language Processing and Data warehouse and Brain Computer Interface.

References

M. Ahmad, N. Wahid, R. A. Hamid, S. Sadiq, A. Mehmood, and G. S. Choi, “Decision Level Fusion Using Hybrid Classifier for Mental Disease Classification,” Computers, Materials and Continua, vol. 72, no. 3, pp. 5041–5058, 2022, doi: 10.32604/cmc.2022.026077.

M. F. Mridha, S. C. Das, M. M. Kabir, A. A. Lima, M. R. Islam, and Y. Watanobe, “Brain-computer interface: advancement and challenges,” Sep. 01, 2021, MDPI. doi: 10.3390/s21175746.

B. J. Baars and N. M. Gage, Cognition, Brain, and Consciousness. Elsevier, 2010. doi: 10.1016/C2009-0-01556-6.

D. Garrett, D. A. Peterson, C. W. Anderson, and M. H. Thaut, “Comparison of linear, nonlinear, and feature selection methods for EEG signal classification,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 11, no. 2, pp. 141–144, Jun. 2003, doi: 10.1109/TNSRE.2003.814441.

T. Alotaiby, F. E. A. El-Samie, S. A. Alshebeili, and I. Ahmad, “A review of channel selection algorithms for EEG signal processing,” EURASIP J Adv Signal Process, vol. 2015, no. 1, Dec. 2015, doi: 10.1186/s13634-015-0251-9.

Z. M. Wang, S. Y. Hu, and H. Song, “Channel Selection Method for EEG Emotion Recognition Using Normalized Mutual Information,” IEEE Access, vol. 7, pp. 143303–143311, 2019, doi: 10.1109/ACCESS.2019.2944273.

Tao Yang, Kai Keng Ang, and Kok Soon Phua, 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society : Learning from the Past, Looking to the Future : July 17-21, 2018, Hawaii Convention Center, Honolulu, Hawaii. IEEE, 2018.

M. Arvaneh, C. Guan, K. K. Ang, and C. Quek, “Optimizing the channel selection and classification accuracy in EEG-based BCI,” IEEE Trans Biomed Eng, vol. 58, no. 6, pp. 1865–1873, Jun. 2011, doi: 10.1109/TBME.2011.2131142.

M. Arvaneh, C. Guan, K. K. Ang, and C. Quek, “OPTIMIZING EEG CHANNEL SELECTION BY REGULARIZED SPATIAL FILTERING AND MULTI BAND SIGNAL DECOMPOSITION.”

Abdullah, I. Faye, and M. R. Islam, “EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives,” Dec. 01, 2022, MDPI.

C. Dai, D. Pi, and S. I. Becker, “Shapelet-Transformed Multi-channel EEG Channel Selection,” ACM Trans Intell Syst Technol, vol. 11, no. 5, Sep. 2020, doi: 10.1145/3397850.

T. Strypsteen and A. Bertrand, “End-to-end learnable EEG channel selection for deep neural networks with Gumbel-softmax,” J Neural Eng, vol. 18, no. 4, p. 0460a9, Aug. 2021, doi: 10.1088/1741-2552/ac115d.

J. Shen et al., “An Optimal Channel Selection for EEG-Based Depression Detection via Kernel-Target Alignment,” IEEE J Biomed Health Inform, vol. 25, no. 7, pp. 2545–2556, Jul. 2021, doi: 10.1109/JBHI.2020.3045718.

M. Bachmann et al., “Methods for classifying depression in single channel EEG using linear and nonlinear signal analysis,” Comput Methods Programs Biomed, vol. 155, pp. 11–17, Mar. 2018, doi: 10.1016/j.cmpb.2017.11.023.

M. Bachmann, J. Lass, and H. Hinrikus, “Single channel EEG analysis for detection of depression,” Biomed Signal Process Control, vol. 31, pp. 391–397, Jan. 2017, doi: 10.1016/j.bspc.2016.09.010.

H. Chang et al., “EEG-based major depressive disorder recognition by selecting discriminative features via stochastic search,” J Neural Eng, vol. 20, no. 2, p. 026021, Apr. 2023, doi: 10.1088/1741-2552/acbe20.

Z. Wang, C. Hu, W. Liu, X. Zhou, and X. Zhao, “EEG-based high-performance depression state recognition,” Front Neurosci, vol. 17, 2023, doi: 10.3389/fnins.2023.1301214.

X. Li, B. Hu, S. Sun, and H. Cai, “EEG-based mild depressive detection using feature selection methods and classifiers,” Comput Methods Programs Biomed, vol. 136, pp. 151–161, Nov. 2016, doi: 10.1016/j.cmpb.2016.08.010.

J. Shen et al., “Depression Recognition From EEG Signals Using an Adaptive Channel Fusion Method via Improved Focal Loss,” IEEE J Biomed Health Inform, vol. 27, no. 7, pp. 3234–3245, Jul. 2023, doi: 10.1109/JBHI.2023.3265805.

S. Khan et al., “A machine learning based depression screening framework using temporal domain features of the electroencephalography signals,” PLoS One, vol. 19, no. 3 MARCH, Mar. 2024, doi: 10.1371/journal.pone.0299127.

C. Te Wu et al., “Resting-state EEG signal for major depressive disorder detection: A systematic validation on a large and diverse dataset,” Biosensors (Basel), vol. 11, no. 12, Dec. 2021, doi: 10.3390/bios11120499.

B. Seifeddine and N. Dib, “A Single-Channel EEG-Based Discrimination of Major Depressive Disorder with Wavelets Features and Machine Learning,” in 6th International Conference on Networking and Advanced Systems, ICNAS 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICNAS59892.2023.10330501.

V. A. Grin-Yatsenko, I. Baas, V. A. Ponomarev, and J. D. Kropotov, “Independent component approach to the analysis of EEG recordings at early stages of depressive disorders,” Clinical Neurophysiology, vol. 121, no. 3, pp. 281–289, Mar. 2010, doi: 10.1016/j.clinph.2009.11.015.

A. Velichko, M. Belyaev, Y. Izotov, M. Murugappan, and H. Heidari, “Neural Network Entropy (NNetEn): Entropy-Based EEG Signal and Chaotic Time Series Classification, Python Package for NNetEn Calculation,” Algorithms, vol. 16, no. 5, May 2023, doi: 10.3390/a16050255.

Z. Li, M. Ruan, J. Chen, and Y. Fang, “Major Depressive Disorder: Advances in Neuroscience Research and Translational Applications,” Jun. 01, 2021, Springer. doi: 10.1007/s12264-021-00638-3.

K. Kroenke, R. L. Spitzer, and J. B. W. Williams, “The PHQ-9 Validity of a Brief Depression Severity Measure.”

P. Riera-Serra et al., “Clinical predictors of suicidal ideation, suicide attempts and suicide death in depressive disorder: a systematic review and meta-analysis,” Eur Arch Psychiatry Clin Neurosci, Oct. 2023, doi: 10.1007/s00406-023-01716-5.

M. Murugappan, S. Yaacob, M. Rizon, and S. Yaacob, “Asymmetric ratio and FCM based salient channel selection for human emotion detection using EEG,” 2008. [Online]. Available: https://www.researchgate.net/publication/228574665

Guyon, I., Weston, J., Barnhill, S. et al. Gene Selection for Cancer Classification using Support Vector Machines. Machine Learning 46, 389–422 (2002).